English
Related papers

Related papers: Policy Optimization with Stochastic Mirror Descent

200 papers

Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently…

Machine Learning · Computer Science 2017-08-10 Farnood Salehi , L. Elisa Celis , Patrick Thiran

Policy gradient methods are a vital ingredient behind the success of modern reinforcement learning. Modern policy gradient methods, although successful, introduce a residual error in gradient estimation. In this work, we argue that this…

Machine Learning · Computer Science 2024-03-05 Pulkit Katdare , Anant Joshi , Katherine Driggs-Campbell

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches…

Machine Learning · Computer Science 2026-02-04 Hai Zhong , Zhuoran Li , Xun Wang , Longbo Huang

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Machine Learning · Computer Science 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

Group Relative Policy Optimization (GRPO), a prominent algorithm within the Reinforcement Learning from Verifiable Rewards (RLVR) framework, has achieved strong results in improving the reasoning capabilities of large language models…

Machine Learning · Computer Science 2026-05-21 Xixiang He , Qiyao Sun , Ao Cheng , Xingming Li , Xuanyu Ji , Hailun Lu , Runke Huang , Qingyong Hu

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative…

Machine Learning · Computer Science 2019-03-14 Yunhao Tang , Mingzhang Yin , Mingyuan Zhou

Safety exploration can be regarded as a constrained Markov decision problem where the expected long-term cost is constrained. Previous off-policy algorithms convert the constrained optimization problem into the corresponding unconstrained…

Machine Learning · Computer Science 2024-10-28 Hengrui Zhang , Youfang Lin , Sheng Han , Shuo Wang , Kai Lv

Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn…

Machine Learning · Computer Science 2026-01-27 Junbo Li , Peng Zhou , Rui Meng , Meet P. Vadera , Lihong Li , Yang Li

Policy mirror descent (PMD) is a general policy optimization framework in reinforcement learning, which can cover a wide range of typical policy optimization methods by specifying different mirror maps. Existing analysis of PMD requires…

Optimization and Control · Mathematics 2025-09-24 Jiacai Liu , Wenye Li , Ke Wei

Recent advances in large reasoning models have leveraged reinforcement learning with verifiable rewards (RLVR) to improve reasoning capabilities. However, scaling these methods typically requires extensive rollout computation and large…

Machine Learning · Computer Science 2025-09-03 Xinyu Tang , Zhenduo Zhang , Yurou Liu , Wayne Xin Zhao , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Competitive multi-agent reinforcement learning in imperfect-information games requires agents to act under partial observability and against adversarial opponents, necessitating stochastic policies. While self-play reinforcement learning…

Machine Learning · Computer Science 2026-05-20 Zhiyuan Fan , Gabriele Farina

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs). However, the sparsity of binary verifier rewards often leads to low efficiency and…

Machine Learning · Computer Science 2026-05-22 Shuo Yang , Jinda Lu , Kexin Huang , Chiyu Ma , Shaohang Wei , Yuyang Liu , Guoyin Wang , Jingren Zhou , Li Yuan

Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the…

Machine Learning · Computer Science 2026-05-22 David Šiška , Yufei Zhang

Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based…

Artificial Intelligence · Computer Science 2017-11-23 Daniel Levy , Stefano Ermon

Recent policy optimization approaches (Schulman et al., 2015a; 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy objectives allow stable and low variance policy learning, but…

Machine Learning · Computer Science 2020-02-24 Marcin B. Tomczak , Dongho Kim , Peter Vrancx , Kee-Eung Kim

On-policy reinforcement learning (RL) algorithms are typically characterized as algorithms that perform policy updates using i.i.d. trajectories collected by the agent's current policy. However, after observing only a finite number of…

Machine Learning · Computer Science 2026-02-11 Nicholas E. Corrado , Josiah P. Hanna

Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving…

Machine Learning · Computer Science 2018-08-10 Ruiyi Zhang , Changyou Chen , Chunyuan Li , Lawrence Carin

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

Robotics · Computer Science 2016-09-13 Yunpeng Pan , Xinyan Yan , Evangelos Theodorou , Byron Boots